© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-65K
    4. 3072
    Prev
    Next
    INDEX
    Explanations

    New Testament

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </h3>
    0.84
    ى
    0.67
    </h6>
    0.65
    </h5>
    0.64
    </em>
    0.62
    你
    0.61
    </h4>
    0.58
    ı
    0.58
    </blockquote>
    0.57
    an
    0.57
    POSITIVE LOGITS
     Testament
    0.63
    чити
    0.56
    более
    0.55
    하신
    0.54
     necesarios
    0.53
    Доброго
    0.52
    ือบ
    0.52
    ्स
    0.51
    ناسب
    0.50
    ﺪ
    0.50
    Activations Density 0.002%

    No Known Activations